ICLR 2025 Conference Submissions

Heterogeneous Federated Learning: A Dual Matching Dataset Distillation Approach
Zhengquan Luo, Xuhui Li, Changyou Chen, Dong An, Shengcai Liao, Peilin Zhao, Yunlong Wang, zhiqiang xu
- 13 Sept 2024 (modified: 22 Mar 2025)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization
Jinlong Li, Dong Zhao, ZEQUN JIE, Elisa Ricci, Lin Ma, Nicu Sebe
- 13 Sept 2024 (modified: 23 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
Chunming He, Chengyu Fang, Yulun Zhang, Longxiang Tang, Jinfa Huang, Kai Li, Zhenhua Guo, Xiu Li, Sina Farsiu
- Published: 22 Jan 2025, Last Modified: 24 Feb 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Algebraic SPD and Correlation Geometry: A Gyro Approach
Rui Wang, Shaocheng Jin, Xiaojun Wu, Xiaoqing Luo, Nicu Sebe, Ziheng Chen
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
MaRS: A Fast Sampler for Mean Reverting Diffusion based on ODE and SDE Solvers
Ao Li, Wei Fang, Hongbo Zhao, Le Lu, Ge Yang, Minfeng Xu
- Published: 22 Jan 2025, Last Modified: 27 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
Fading Focus: Mitigating Visual Attention Degradation in Large Vision-Language Models
Chenhang Cui, Jiabing Yang, Yiyang Zhou, Peng Xia, Ying Wei, Huaxiu Yao
- 13 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
A Self-Supervised PINN for Inertial Pose and Dynamics Estimations
Markus Gambietz, Eva Dorschky, Marcel Schöckel, Jörg Miehling, Anne D. Koelewijn
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks
Yijie Guo, Bingjie Tang, Iretiayo Akinola, Dieter Fox, Abhishek Gupta, Yashraj Narang
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Spotlight
- Readers: Everyone
AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding
Chang Lei, Huan Lei
- 13 Sept 2024 (modified: 19 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
LSTT:LONG SHORT-TERM TRANSFORMER FOR VIDEO SMALL OBJECT DETECTION
Wenbo Liu, Jinsheng Xiao, Yang Jianfeng, Yunhua Chen, Zhongyuan Wang, Jiayi Ma
- 13 Sept 2024 (modified: 13 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong, Lei Zhu, Shuicheng YAN
- Published: 22 Jan 2025, Last Modified: 28 Feb 2025
- ICLR 2025 Poster
- Readers: Everyone
AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation
Jiafei Duan, Wilbert Pumacay, Nishanth Kumar, Yi Ru Wang, Shulin Tian, Wentao Yuan, Ranjay Krishna, Dieter Fox, Ajay Mandlekar, Yijie Guo
- Published: 22 Jan 2025, Last Modified: 07 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
Shapley-Guided Utility Learning for Effective Graph Inference Data Valuation
Hongliang Chi, Qiong Wu, Zhengyi Zhou, Yao Ma
- Published: 22 Jan 2025, Last Modified: 01 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
LLMs Boost the Performance of Decision Trees on Tabular Data across Sample Sizes
Bethmage Mayuka Jayawardhana, Renbo Tu, Samuel Dooley, Valeriia Cherepanova, Andrew Gordon Wilson, Frank Hutter, Colin White, Tom Goldstein, Micah Goldblum
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation
Brian Nlong Zhao, Yuhang Xiao, Jiashu Xu, XINYANG JIANG, Yifan Yang, Dongsheng Li, Laurent Itti, Vibhav Vineet, Yunhao Ge
- Published: 22 Jan 2025, Last Modified: 02 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
SeeThruAnything: Learning to Remove Any Obstructions Across Distributions
Junhang Li, Yu Guo, Chuhua XIAN, Shengfeng He
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
GyroAtt: A Gyro Attention Framework for Matrix Manifolds
Rui Wang, Chen Hu, Xiaojun Wu, Xiaoning Song, Nicu Sebe, Ziheng Chen
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
UOE: Unlearning One Expert is Enough for Mixture-of-Experts LLMs
Haomin Zhuang, Yihua Zhang, Kehan Guo, Jinghan Jia, Gaowen Liu, Sijia Liu, Xiangliang Zhang
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Agent-as-a-Judge: Evaluating Agents with Agents
Mingchen Zhuge, Changsheng Zhao, Dylan R. Ashley, Wenyi Wang, Dmitrii Khizbullin, Yunyang Xiong, Zechun Liu, Ernie Chang, Raghuraman Krishnamoorthi, Yuandong Tian, Yangyang Shi, Vikas Chandra, Jürgen Schmidhuber
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
FMBench: Benchmarking Fairness in Multimodal Large Language Models on Medical Tasks
Peiran Wu, Che Liu, Canyu Chen, Jun Li, Cosmin I. Bercea, Rossella Arcucci
- 13 Sept 2024 (modified: 12 Nov 2024)
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
Learning the Language of Protein Structure
Jérémie DONA, Benoit Gaujac, Timothy Atkinson, Thomas PIERROT, Thomas D Barrett
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Personality Alignment of Large Language Models
Minjun Zhu, Yixuan Weng, Linyi Yang, Yue Zhang
- Published: 22 Jan 2025, Last Modified: 26 Mar 2025
- ICLR 2025 Poster
- Readers: Everyone
SQT -- rough conservative actor critic
Nitsan Soffair, Gilad Katz, Dotan Di Castro, Orly Avner, Shie Mannor
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Locking Down the Finetuned LLMs Safety
Minjun Zhu, Yixuan Weng, Linyi Yang, Yifan Wei, Ningyu Zhang, Yue Zhang
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone
Efficient Long-range Language Modeling with Self-supervised Causal Retrieval
Xiang Hu, Zhihao Teng, Wei Wu, Kewei Tu
- 13 Sept 2024 (modified: 05 Feb 2025)
- Submitted to ICLR 2025
- Readers: Everyone